Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix categorize_transactions to account for variations in LLM response, added docs #7

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
venv
27 changes: 27 additions & 0 deletions How_To_Run.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
# Prerequisites:
- [Git](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git)
- [Python](https://www.python.org/downloads/)
- [Ollama](https://github.com/ollama/ollama?tab=readme-ov-file)
- [VSCode](https://code.visualstudio.com/download)

# Setup

```zsh
git clone [email protected]:thu-vu92/local-llms-analyse-finance.git

cd local-llms-analyse-finance && code .

# Once opened in VSCode, Install any extenstions recommended for Jupyter and Python.

# Might serve you better to setup a python virtual env for the project
python3 -m venv venv && source venv/bin/activate
pip3 install pydantic pandas
```

- Select the newly created python environment at top right of the Jupyter file in VSCode.
![Select virtual env](./screenshots/select_kernel.png)

- "Run All" in categorize_expenses_with_validation.ipynb file. You might have to uncomment the top pip3 install line since you're likely to lack the dependencies (same for other files).
![Run all](./screenshots/run_all.png)

- Now that the categorized transactions are generated, 'Run All' in dashboard.ipynb (be mindful of dependencies) and your dashboard should be up and launch on local browser.
Loading